Merge branch 'master' into master

Author: ehanson8

.gitignore

@@ -46,6 +46,7 @@ Network Trash Folder
 Temporary Items
 .apdisk
 secrets.py
+secretsProd.py
 *.pyc
 data/*
 !data/.keep
@@ -55,3 +56,4 @@ data/*
 local/*
 *.xml
 *.xslx
+*.txt

README.md

@@ -8,6 +8,10 @@ All of these scripts require a secrets.py file in the same directory that must c
 	user='[user name]'
 	password='[password]'
 
+This secrets.py file will be ignored according to the repository's .gitignore file so that ArchivesSpace login details will not be inadvertently exposed through GitHub.
+
+If you are using both a development server and a production server, you can create a separate secrets.py file with a different name (e.g. secretsProd.py) and containing the production server information. When running each of these scripts, you will be prompted to enter the file name (e.g 'secretsProd' without '.py') of an alternate secrets file. If you skip the prompt or incorrectly type the file name, the scripts will default to the information in the secrets.py file. This ensures that you will only access the production server if you really intend to.
+
 ## Scripts
 
 #### [addBibNumbersAndPost.py](/addBibNumbersAndPost.py)
@@ -67,6 +71,9 @@ Retrieves all of the top containers from a particular repository into a JSON fil
 #### [getUrisAndIds.py](getUrisAndIds.py)
 For the specified record type, retrieves URI and the 'id_0,' 'id_1,' 'id_2,' 'id_3,' and a concatenated version of all the 'id' fields.
 
+#### [modifyDigitalObjectUrls.py](/modifyDigitalObjectUrls.py)
+Based on user input, replaces a string in the URLs in both the 'Identifier' and 'File URI' fields for digital objects across the repository.
+
 #### [postContainersFromCSV.py](/postContainersFromCSV.py)
 Creates instances (consisting of top_containers) from a separate CSV file. The CSV file should have two columns, indicator and barcode. The directory where this file is stored must match the directory in the filePath variable. The script will prompt you first for the exact name of the CSV file, and then for the exact resource or accession to attach the containers to.
 

addBibNumbersAndPost.py

@@ -3,6 +3,17 @@
 import secrets
 import time
 import csv
+from datetime import datetime
+
+secretsVersion = raw_input('To edit production server, enter the name of the secrets file: ')
+if secretsVersion != '':
+    try:
+        secrets = __import__(secretsVersion)
+        print 'Editing Production'
+    except ImportError:
+        print 'Editing Development'
+else:
+    print 'Editing Development'
 
 startTime = time.time()
 
@@ -16,7 +27,7 @@
 
 urisBibs = csv.DictReader(open(''))
 
-f=csv.writer(open('bibNumberPush.csv', 'wb'))
+f=csv.writer(open('bibNumberPush'+datetime.now().strftime('%Y-%m-%d %H.%M.%S')+'.csv', 'wb'))
 f.writerow(['uri']+['existingValue']+['bibNum'])
 
 for row in urisBibs:

dateCheck.py

@@ -4,6 +4,16 @@
 import time
 import csv
 
+secretsVersion = raw_input('To edit production server, enter the name of the secrets file: ')
+if secretsVersion != '':
+    try:
+        secrets = __import__(secretsVersion)
+        print 'Editing Production'
+    except ImportError:
+        print 'Editing Development'
+else:
+    print 'Editing Development'
+
 startTime = time.time()
 
 baseURL = secrets.baseURL

eadToCsv.py

@@ -7,6 +7,10 @@ def extractValuesFromComponentLevel (componentLevel):
         unittitle = componentLevel.find('did').find('unittitle').text.replace('\n','').encode('utf-8')
         controlAccess = []
         originationList = []
+        try:
+            physdesc = componentLevel.find('did').find('physdesc').text.replace('\n','').encode('utf-8')
+        except:
+            physdesc = ''
         try:
             unitdate = componentLevel.find('did').find('unitdate')
             dateExpression = unitdate.text.encode('utf-8').replace('\n','').replace('              ',' ').replace('            ',' ').encode('utf-8')
@@ -73,22 +77,19 @@ def extractValuesFromComponentLevel (componentLevel):
             originationList = ''
         global sortOrder
         sortOrder += 1
-        f.writerow([sortOrder]+[level]+[componentLevelLabel]+[containerType1]+[container1]+[containerType2]+[container2]+[unittitle]+[dateExpression]+[dateType]+[beginDate]+[endDate]+[scopecontent]+[controlAccess]+[originationList]+[containerId1]+[containerId2])
+        f.writerow([sortOrder]+[level]+[componentLevelLabel]+[containerType1]+[container1]+[containerType2]+[container2]+[unittitle]+[physdesc]+[dateExpression]+[dateType]+[beginDate]+[endDate]+[scopecontent]+[controlAccess]+[originationList]+[containerId1]+[containerId2])
 
-filepath = '/home/mjanowi3/archivesspace-api'
 filepath = ''
-fileName = 'Coll.011.xml'
+fileName = 'Coll.004_20181012_144804_UTC__ead.xml'
 xml = open(filepath+fileName)
 
-
-
 f=csv.writer(open(filepath+'eadFields.csv', 'wb'))
-f.writerow(['sortOrder']+['hierarchy']+['level']+['containerType1']+['container1']+['containerType2']+['container2']+['unittitle']+['dateexpression']+['datetype']+['begindate']+['enddate']+['scopecontent']+['controlAccess']+['origination']+['containerId1']+['containerId2'])
+f.writerow(['sortOrder']+['hierarchy']+['level']+['containerType1']+['container1']+['containerType2']+['container2']+['unittitle']+['physdesc']+['dateexpression']+['datetype']+['begindate']+['enddate']+['scopecontent']+['controlAccess']+['origination']+['containerId1']+['containerId2'])
 upperComponentLevels = BeautifulSoup(xml, 'lxml').find('dsc').find_all('c01')
 sortOrder = 0
 for upperComponentLevel in upperComponentLevels:
     componentLevelLabel = upperComponentLevel['level']
-    unittitle = upperComponentLevel.find('did').find('unittitle').text.encode('utf-8')
+    unittitle = upperComponentLevel.find('did').find('unittitle').text.encode('utf-8').replace('\n','').replace('              ', ' ')
     try:
         unitdate = upperComponentLevel.find('did').find('unitdate')
         dateExpression = unitdate.text.encode('utf-8').replace('\n','').replace('              ',' ').replace('            ',' ').encode('utf-8')
@@ -117,7 +118,7 @@ def extractValuesFromComponentLevel (componentLevel):
     except:
         scopecontent = ''
     sortOrder += 1
-    f.writerow([sortOrder]+['c01']+[componentLevelLabel]+['']+['']+['']+['']+[unittitle]+[dateExpression]+[dateType]+[beginDate]+[endDate]+[scopecontent]+['']+['']+['']+[''])
+    f.writerow([sortOrder]+['c01']+[componentLevelLabel]+['']+['']+['']+['']+[unittitle]+['']+[dateExpression]+[dateType]+[beginDate]+[endDate]+[scopecontent]+['']+['']+['']+[''])
 
     componentLevelArray = upperComponentLevel.find_all('c02')
     for componentLevel in componentLevelArray:

getAccessionUDFs.py

@@ -4,16 +4,17 @@
 import time
 import csv
 
-startTime = time.time()
+secretsVersion = raw_input('To edit production server, enter the name of the secrets file: ')
+if secretsVersion != '':
+    try:
+        secrets = __import__(secretsVersion)
+        print 'Editing Production'
+    except ImportError:
+        print 'Editing Development'
+else:
+    print 'Editing Development'
 
-def findKey(d, key):
-    if key in d:
-        yield d[key]
-    for k in d:
-        if isinstance(d[k], list) and k == 'children':
-            for i in d[k]:
-                for j in findKey(i, key):
-                    yield j
+startTime = time.time()
 
 baseURL = secrets.baseURL
 user = secrets.user

getAccessions.py

@@ -3,6 +3,16 @@
 import secrets
 import time
 
+secretsVersion = raw_input('To edit production server, enter the name of the secrets file: ')
+if secretsVersion != '':
+    try:
+        secrets = __import__(secretsVersion)
+        print 'Editing Production'
+    except ImportError:
+        print 'Editing Development'
+else:
+    print 'Editing Development'
+
 startTime = time.time()
 
 baseURL = secrets.baseURL

getAllArchivalObjectTitles.py

@@ -4,6 +4,16 @@
 import time
 import csv
 
+secretsVersion = raw_input('To edit production server, enter the name of the secrets file: ')
+if secretsVersion != '':
+    try:
+        secrets = __import__(secretsVersion)
+        print 'Editing Production'
+    except ImportError:
+        print 'Editing Development'
+else:
+    print 'Editing Development'
+
 startTime = time.time()
 
 baseURL = secrets.baseURL

getArchivalObjectCountByResource.py

@@ -4,6 +4,16 @@
 import time
 import csv
 
+secretsVersion = raw_input('To edit production server, enter the name of the secrets file: ')
+if secretsVersion != '':
+    try:
+        secrets = __import__(secretsVersion)
+        print 'Editing Production'
+    except ImportError:
+        print 'Editing Development'
+else:
+    print 'Editing Development'
+
 startTime = time.time()
 
 def findKey(d, key):

getArchivalObjectRefIdsForResource.py

@@ -4,6 +4,16 @@
 import time
 import csv
 
+secretsVersion = raw_input('To edit production server, enter the name of the secrets file: ')
+if secretsVersion != '':
+    try:
+        secrets = __import__(secretsVersion)
+        print 'Editing Production'
+    except ImportError:
+        print 'Editing Development'
+else:
+    print 'Editing Development'
+
 startTime = time.time()
 
 def findKey(d, key):